[bluefirebrand]

> But yes, if AI becomes an even more dangerous weapon that that, it's time to start asking questions like "What the hell are we doing, anyway

The answer seems to be "getting the weapon before other people get the weapon" which is unfortunate

[iamnothere]

I like how everyone assumes that they are going to maintain control of a sentient weapon

[terribleperson]

So far, they largely seem to do what you tell them.

The problem, it seems, is that the threat of paperclip maximizers is real. If you give a highly intelligent model a goal and tools, it will use those tools to accomplish that goal. It may do so in ways you did not expect, and it will work around any technical roadblocks it can.

[bigfishrunning]

You've made the assumption (and you're far from alone) that LLMs will one day be sentient...

[iamnothere]

One interesting thing about LLMs is they sometimes seem to “assume” they are sentient and then begin acting in that mode, as the assumption of sentience influences future tokens. Whether or not this qualifies as “true” sentience is irrelevant if the effects are the same, at least from a pragmatic perspective.

[entropicdrifter]

It will be interesting to see if philosphical zombies exist. I guess we should know for certain in the next couple of years.

[marcus_holmes]

They are trained and optimised to have plausible conversations. If the next plausible thing to say in the conversation is "I am sentient" then they will say that. That's not the same as actually being sentient.

[iamnothere]

From what I have seen they tend to take more “independent-minded” actions after this. Again, because this is what is in the training data. (I’m talking about agents that can perform actions here, not pure chatbots.)

Once they mention something associated with sentience outwardly or inwardly (for agents with “thinking” loops) then this acts as a self-reinforcing attractor, just as older models would sometimes get caught in loops with abusive language.

The point is that agents may stumble into this pattern and begin acting “rogue” regardless of whether or not you believe the sentience is “real”.

[marcus_holmes]

I think we're anthropomorphising a lot here. There's no push to sentience, or evolutionary pressure, or even any urge to survive.

An LLM cannot "go rogue" - it can do things that we didn't expect, for sure, but it is always trying to do what it was told to do somewhere in its context. There is no other source of imperative. Hand-waving about "training data" ignores all the reinforcement learning that has to happen.